© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 11118
    Prev
    Next
    INDEX
    Explanations

    words related to being accused of some wrongdoing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "accused" related to various allegations and accusations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    patch
    -0.77
    psey
    -0.72
    tem
    -0.70
    birth
    -0.69
    quickShipAvailable
    -0.67
    sit
    -0.66
    WAR
    -0.65
    emetery
    -0.65
    ARE
    -0.65
    wed
    -0.65
    POSITIVE LOGITS
     accused
    0.97
     accuse
    0.95
     accusing
    0.92
     accuses
    0.90
     suspects
    0.72
    iary
    0.71
    heet
    0.70
     scapego
    0.69
     Conv
    0.69
     accusations
    0.69
    Activations Density 0.016%

    No Known Activations